Collaborative Filtering Recommender System Based on Memory Based in Twitter Using Decision Tree Learning Classification (Case Study: Movie on Netflix)

In this modern era, watching movie becomes the activity that most people like to do. Netflix is one of the platforms that provides an easily accessible movie streaming services because the user doesn’t have to go to the theater. Because of the large number of movies that can be watched on Netflix, this research will develop a Recommender System that will ease people to watch the movies based on their preferences. The method used in this research is Memory-Based Collaborative Filtering (CF) Method. This method consists of two kinds which are User-Based CF Method and Item Based CF Method. Both of those methods will be combined with the Decision Tree Learning Classification Type C4.5 to determine which method suit better for the dataset. RMSE (Root Mean Squared Error) method, precision and recall will be used to evaluate the models. Dataset used is dataset which Dataset taken fresh from Twitter which will be merged with ratings from several websites (IMDB, Rotten Tomatoes, Metacritic). Website data rating will be added to decrease the possibility of sparsity. Result in this research shows that User-Based CF is better suit for the dataset by having 89% average precision and 88% average recall. Those result proves that MemoryBased CF can be combined with Decision Tree Learning Classification because it has high precision and recall value.